Загрузка данных
- name: nexus-blackbox-proxy
rules:
- alert: NexusProxyTargetDown
annotations:
summary: "Proxy target {{`{{ $labels.instance }}`}} is down."
description: "Blackbox probe through Nexus proxy failed for {{`{{ $labels.instance }}`}} for 3 minutes."
dashboard_url: "{{ .Values.prometheusRules.params.dashboard_url }}"
runbook_url: "{{ .Values.prometheusRules.params.runbook_url }}"
expr: probe_success{job="nexus-proxy-targets"} == 0
for: 3m
labels:
team: sre
service: nexus
component: proxy
environment: production
severity: critical
- alert: NexusProxyHighLatency
annotations:
summary: "High Nexus proxy latency for {{`{{ $labels.instance }}`}}."
description: "Proxy request to {{`{{ $labels.instance }}`}} has p95 latency above 3 seconds for 5 minutes."
dashboard_url: "{{ .Values.prometheusRules.params.dashboard_url }}"
runbook_url: "{{ .Values.prometheusRules.params.runbook_url }}"
expr: quantile_over_time(0.95, probe_duration_seconds{job="nexus-proxy-targets"}[5m]) > 3
for: 5m
labels:
team: sre
service: nexus
component: proxy
environment: production
severity: warning
<<<<<<< HEAD
- alert: NexusProxySSLCertificateExpiringSoon
expr: probe_ssl_earliest_cert_expiry{job="nexus-blackbox-proxy"} - time() < 86400 * 30
for: 1h
labels:
severity: warning
component: proxy
service: blackbox
annotations:
summary: "SSL certificate expiring soon for {{`{{ $labels.instance }}`}}"
description: "SSL certificate for {{`{{ $labels.instance }}`}} will expire in {{`{{ $value | humanizeDuration }}`}}."
- alert: NexusProxySSLCertificateExpired
expr: probe_ssl_earliest_cert_expiry{job="nexus-blackbox-proxy"} - time() < 0
for: 1m
labels:
severity: critical
component: proxy
service: blackbox
annotations:
summary: "SSL certificate expired for {{`{{ $labels.instance }}`}}"
description: "SSL certificate for {{`{{ $labels.instance }}`}} has expired."
- alert: NexusProxyHTTP4xxError
expr: probe_http_status_code{job="nexus-blackbox-proxy"} >= 400 and probe_http_status_code{job="nexus-blackbox-proxy"} < 500
for: 1m
labels:
severity: warning
component: proxy
service: blackbox
annotations:
summary: "HTTP 4xx status for {{`{{ $labels.instance }}`}}"
description: "Proxy request to {{`{{ $labels.instance }}`}} returned HTTP 4xx status code {{`{{ $value }}`}}."
- alert: NexusProxyHTTP5xxError
expr: probe_http_status_code{job="nexus-blackbox-proxy"} >= 500 and probe_http_status_code{job="nexus-blackbox-proxy"} < 600
for: 1m
labels:
severity: warning
component: proxy
service: blackbox
annotations:
summary: "HTTP 5xx status for {{`{{ $labels.instance }}`}}"
description: "Proxy request to {{`{{ $labels.instance }}`}} returned HTTP 5xx status code {{`{{ $value }}`}}."
- alert: NexusBlackboxExporterDown
expr: up{job="nexus-blackbox-exporter",namespace="nexus"} == 0
for: 5m
labels:
severity: critical
component: monitoring
service: blackbox
annotations:
summary: "Blackbox exporter is down"
description: "Blackbox exporter pod {{`{{ $labels.pod }}`}} in cluster {{`{{ $labels.cluster }}`}} is not responding to scrape requests."
- alert: NexusProxyMultipleTargetsDown
expr: count(probe_success{job="nexus-blackbox-proxy"} == 0) > 2
for: 1m
labels:
severity: critical
component: proxy
service: blackbox
annotations:
summary: "Multiple proxy targets are unreachable"
description: "{{`{{ $value }}`}} targets are currently unreachable through the proxy. This might indicate a proxy outage."
=======
- alert: NexusProxyCriticalLatency
annotations:
summary: "Critical Nexus proxy latency for {{`{{ $labels.instance }}`}}."
description: "Proxy request to {{`{{ $labels.instance }}`}} has p99 latency above 5 seconds for 3 minutes."
dashboard_url: "{{ .Values.prometheusRules.params.dashboard_url }}"
runbook_url: "{{ .Values.prometheusRules.params.runbook_url }}"
expr: quantile_over_time(0.99, probe_duration_seconds{job="nexus-proxy-targets"}[5m]) > 5
for: 3m
labels:
team: sre
service: nexus
component: proxy
environment: production
severity: critical
- alert: NexusProxyCertExpiringSoon
annotations:
summary: "SSL certificate expiring soon for {{`{{ $labels.instance }}`}}."
description: "SSL certificate for {{`{{ $labels.instance }}`}} will expire in {{`{{ $value | humanizeDuration }}`}}."
dashboard_url: "{{ .Values.prometheusRules.params.dashboard_url }}"
runbook_url: "{{ .Values.prometheusRules.params.runbook_url }}"
expr: probe_ssl_earliest_cert_expiry{job="nexus-proxy-targets"} - time() < 86400 * 30
for: 1h
labels:
team: sre
service: nexus
component: certificates
environment: production
severity: warning
>>>>>>> origin/master